def get_ann_trained_on_patterns(training_patterns, training_iterations):
ann = NeocorticalNetwork(49, 30, 49, 0.01, 0.9)
# training:
for x in xrange(training_iterations):
ann.train(training_patterns)
return ann
def global_sequential_FFBP_training(ss, training_iterations):
io_dim = 49
ann = NeocorticalNetwork(io_dim, 30, io_dim, 0.01, 0.9)
training_set = training_patterns_associative[:5*ss]
for i in range(training_iterations):
ann.train(training_set)
return ann
def iterate_over_experiments_suite_span_output_demo_local(start_index, stop_index):
ann = NeocorticalNetwork(49, 30, 49, 0.01, 0.9)
for exp_index in range(start_index, stop_index):
current_chaotic_patterns, current_pseudopatterns = \
Tools.retrieve_patterns_for_consolidation(exp_index, exp_index%4 + 2) # 2-5 looped
training_set = []
t0 = time.time()
ann.reset()
for cp_subset in current_chaotic_patterns:
training_subset = []
for cp in cp_subset:
training_subset.append([cp[1], cp[1]])
for i in range(15):
ann.train(training_subset)
results_line = 'Neocortical module consolidation. Output as IO. Exp#'+str(exp_index)+\
'\n'+str(i+1)+' iters: g='+str(evaluate_goodness_of_fit(ann, get_target_patterns(exp_index%4+2)))
ann.reset()
for cp_subset in current_chaotic_patterns:
training_subset = []
for cp in cp_subset:
training_subset.append([cp[1], cp[1]])
for i in range(200):
ann.train(training_subset)
results_line += '\n'+str(i+1)+' iters: g=' + str(evaluate_goodness_of_fit(ann, get_target_patterns(exp_index % 4 + 2)))
t1 = time.time()
print 'Trained and evaluated performance in '+'{:8.3f}'.format(t1-t0), 'seconds'
print results_line
Tools.append_line_to_log(results_line)
return ann
def traditional_training_with_catastrophic_interference(ss, training_iterations):
io_dim = 49
ann = NeocorticalNetwork(io_dim, 30, io_dim, 0.01, 0.9)
training_set = training_patterns_associative[:25]
# ss = 2
for i in range(5):
for training_iteration in range(training_iterations):
ann.train(training_set[i*ss:i*ss+ss])
# for j in range(ss*5):
# Tools.show_image_from(ann.get_IO(training_set[j][0])[1])
return ann
def train_on_chaotic_patterns():
chaotic_outs, rand_ins = retrieve_chaotic_patterns_from_exp_num(1)
# print "len(chaotic_outs):", len(chaotic_outs)
chaotic_patts = []
for i in range(len(chaotic_outs)):
chaotic_patts.append([])
for j in range(len(chaotic_outs[i])):
chaotic_patts[i].append([rand_ins[i][j], chaotic_outs[i][j]])
io_dim = 49
ann = NeocorticalNetwork(io_dim, 30, io_dim, 0.01, 0.9)
training_set = []
for i in range(5):
training_set += chaotic_patts[i]
ann.train(chaotic_patts[i])
for train_iters in range(10):
pass
return ann
def iterate_over_experiments_suite(start_index, stop_index, scheme_num):
ann = NeocorticalNetwork(49, 30, 49, 0.01, 0.9)
for exp_index in range(start_index, stop_index):
current_chaotic_patterns, current_pseudopatterns = \
Tools.retrieve_patterns_for_consolidation(exp_index, exp_index%4 + 2) # 2-5 looped
training_set = get_training_set_from_patterns_in_scheme_full_set(current_chaotic_patterns,
current_pseudopatterns, scheme_num)
t0 = time.time()
ann.reset()
for i in range(15):
ann.train(training_set)
results_line = 'Neocortical module consolidation. Scheme: '+str(scheme_num)+'. Exp#'+str(exp_index)+ \
'\n'+str(i+1)+' iters: g='+str(evaluate_goodness_of_fit(ann, get_target_patterns(exp_index%4+2)))
ann.reset()
for i in range(200):
ann.train(training_set)
results_line += '\n'+str(i+1)+' iters: g=' + str(evaluate_goodness_of_fit(ann, get_target_patterns(exp_index % 4 + 2)))
t1 = time.time()
print 'Trained and evaluated performance in '+'{:8.3f}'.format(t1-t0), 'seconds'
print results_line
Tools.append_line_to_log(results_line)
